Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3299 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.5804. Min Range: -0.5804

Max Act: 0.5804. Min Act: -0.0001

Data Index: 936842 (C4 (Web Text))

Max Activating Token Index: 820

Text #1

Max Range: 0.5804. Min Range: -0.5804

Max Act: 0.5748. Min Act: -0.0001

Data Index: 857695 (C4 (Web Text))

Max Activating Token Index: 446

Text #2

Max Range: 0.5804. Min Range: -0.5804

Max Act: 0.5196. Min Act: -0.0001

Data Index: 639203 (C4 (Web Text))

Max Activating Token Index: 538

Text #3

Max Range: 0.5804. Min Range: -0.5804

Max Act: 0.4646. Min Act: -0.0001

Data Index: 1090917 (C4 (Web Text))

Max Activating Token Index: 319

Text #4

Max Range: 0.5804. Min Range: -0.5804

Max Act: 0.4392. Min Act: -0.0001

Data Index: 184468 (C4 (Web Text))

Max Activating Token Index: 414

Text #5

Max Range: 0.5804. Min Range: -0.5804

Max Act: 0.4538. Min Act: -0.0001

Data Index: 611443 (C4 (Web Text))

Max Activating Token Index: 161

Text #6

Max Range: 0.5804. Min Range: -0.5804

Max Act: 0.4286. Min Act: -0.0001

Data Index: 1247854 (C4 (Web Text))

Max Activating Token Index: 994

Text #7

Max Range: 0.5804. Min Range: -0.5804

Max Act: 0.4017. Min Act: -0.0001

Data Index: 900279 (C4 (Web Text))

Max Activating Token Index: 210

Text #8

Max Range: 0.5804. Min Range: -0.5804

Max Act: 0.4171. Min Act: -0.0001

Data Index: 708479 (C4 (Web Text))

Max Activating Token Index: 485

Text #9

Max Range: 0.5804. Min Range: -0.5804

Max Act: 0.4124. Min Act: -0.0001

Data Index: 696565 (C4 (Web Text))

Max Activating Token Index: 517

Text #10

Max Range: 0.5804. Min Range: -0.5804

Max Act: 0.4094. Min Act: -0.0000

Data Index: 1171930 (C4 (Web Text))

Max Activating Token Index: 913

Text #11

Max Range: 0.5804. Min Range: -0.5804

Max Act: 0.3884. Min Act: -0.0001

Data Index: 92162 (C4 (Web Text))

Max Activating Token Index: 764

Text #12

Max Range: 0.5804. Min Range: -0.5804

Max Act: 0.3963. Min Act: -0.0001

Data Index: 654100 (C4 (Web Text))

Max Activating Token Index: 931

Text #13

Max Range: 0.5804. Min Range: -0.5804

Max Act: 0.3940. Min Act: -0.0001

Data Index: 394312 (C4 (Web Text))

Max Activating Token Index: 647

Text #14

Max Range: 0.5804. Min Range: -0.5804

Max Act: 0.3877. Min Act: -0.0001

Data Index: 1244240 (C4 (Web Text))

Max Activating Token Index: 209

Text #15

Max Range: 0.5804. Min Range: -0.5804

Max Act: 0.3833. Min Act: -0.0001

Data Index: 929500 (C4 (Web Text))

Max Activating Token Index: 252

Text #16

Max Range: 0.5804. Min Range: -0.5804

Max Act: 0.3496. Min Act: -0.0001

Data Index: 514951 (C4 (Web Text))

Max Activating Token Index: 718

Text #17

Max Range: 0.5804. Min Range: -0.5804

Max Act: 0.3842. Min Act: -0.0001

Data Index: 1176426 (C4 (Web Text))

Max Activating Token Index: 966

Text #18

Max Range: 0.5804. Min Range: -0.5804

Max Act: 0.3691. Min Act: -0.0001

Data Index: 678439 (C4 (Web Text))

Max Activating Token Index: 511

Text #19

Max Range: 0.5804. Min Range: -0.5804

Max Act: 0.3994. Min Act: -0.0001

Data Index: 715808 (C4 (Web Text))

Max Activating Token Index: 638